Existing methods for detecting music plagiarism rely on diverse criteria but remain inherently subjective. Altered audio files (e.g., speed adjustments, pitch changes, etc.) are difficult to accurately determine infringement using traditional similarity measures. The ability to detect file modifications, alongside plagiarized content, is critical in protecting copyright in complex musical environments and holds considerable promise for real-world applications. This study utilizes Graph Attention Network (GAT) framework to improve the precision of similarity assessments between songs. Experimental evaluations demonstrate that the proposed method achieves a 7% improvement in detecting plagiarized and altered audio files compared to conventional non-network-based models. These findings underscore the efficacy of leveraging graph edge attention to enhance acoustic similarity analysis within the network.

This paper employs satellite imagery and machine learning approach to analyze regional disparities in human development (HDI) and multidimensional poverty (MPI). Concentrating on 213 subnational regions worldwide, this study strategically selects countries based on the Human Development Index (HDI), Gini coefficient, and the Theil-T index as measures of deprivation and inequality. The utilization of Google Static Map API and Convolutional Neural Networks (CNNs), facilitates the comprehensive analysis of these indicators. The findings challenge uniform development assumptions in nations, providing refined insights for targeted policy interventions. This quantitative approach, merging satellite technology and artificial intelligence, offers a significant contribution to understanding sustainable development.

This research is centered on the development of a BERT-based metric for greenwashing, designed to address the existing limitations inherent in ESG assessment methodologies. Unlike standard assessments, ESG-BERT considers real-time policy details and reduces the risk of inaccurate evaluations and greenwashing. We employed ESG-BERT along with financial and environmental data to predict greenwashing among Korean KOSPI200 companies. By using advanced machine learning models like ANN, LR, RF, and XGB, the study found that XGB performs best in predicting greenwashing. Furthermore, the study compares greenwashing predictions between companies with top5 and bottom5 ESG ratings. The results showed better performance for the top 5 companies compared to the bottom 5 companies.

Measuring the impact of tourism on society is important for efficient tourism planning and budgeting. Considerable amount of financial resources has been allocated for tourism promotional efforts. Therefore, it is important to understand how well promotional efforts have stimulated tourism social impacts. This study aims to predict the UNWTO promotional video views and its resulting impact on society. A CNN model with VGG16 was used to classify videos and images into clusters and RGB models. Quantitative analysis was conducted to predict video views and annual GDP as a societal impact. Our model performance for predicting official video views reveals strong relationship between image characteristics and promotional video views. Most notably, the strong correlation between image/video data and countries’ GDP growth rate highlighted by the model’s performance illuminates the potential of image data as a predictive tool in understanding the economic impacts of tourism particularly in rural areas.

The technology transfer is crucial in strategic planning for the manufacturing industry. The transfer of patents, with a focus on the importance of licensing and selling, has been emphasized as a foundational element of innovation within the manufacturing sector. This paper introduces a machine learning approach incorporating detailed financial data from manufacturing firms and patent information from the USPTO, to predicts patent transfers as key indicators of patent evaluation. This is achieved by using BERT to convert textual data into numerical vectors, combined with financial metrics, to project patent values as reflected in the number of assignments, claim numbers, and citations. Our findings highlight the significant role of real time analytics in understanding the intricacies of patent transfer activities. This research not only offers an insight into the intrinsic value of patents but also reveals the efficacy of BERT analysis in navigating the intricate nexus of patent information and manufacturing data, enhancing the understanding of patent transfer and its relation to commercialization.